Merge commit '9b3a04d30691e85b77e63f75f5f26a93c3a000cd'

* commit '9b3a04d30691e85b77e63f75f5f26a93c3a000cd':
  x86: Move duplicated put_pixels{8|16}_mmx functions into their own file

Merged-by: Michael Niedermayer <michaelni@gmx.at>

5 files changed, 110 insertions, 135 deletions

diff --git a/libavcodec/x86/Makefile b/libavcodec/x86/Makefile
index 35c82a8..ad61b6a 100644
--- a/libavcodec/x86/Makefile
+++ b/libavcodec/x86/Makefile
@@ -10,7 +10,8 @@ OBJS-$(CONFIG_H264CHROMA)              += x86/h264chroma_init.o
 OBJS-$(CONFIG_H264DSP)                 += x86/h264dsp_init.o
 OBJS-$(CONFIG_H264PRED)                += x86/h264_intrapred_init.o
 OBJS-$(CONFIG_H264QPEL)                += x86/h264_qpel.o
-OBJS-$(CONFIG_HPELDSP)                 += x86/hpeldsp_init.o
+OBJS-$(CONFIG_HPELDSP)                 += x86/fpel_mmx.o                \
+                                          x86/hpeldsp_init.o
 OBJS-$(CONFIG_LPC)                     += x86/lpc.o
 OBJS-$(CONFIG_MLP_DECODER)             += x86/mlpdsp.o
 OBJS-$(CONFIG_MPEGAUDIODSP)            += x86/mpegaudiodsp.o
@@ -36,6 +37,7 @@ OBJS-$(CONFIG_XMM_CLOBBER_TEST)        += x86/w64xmmtest.o
 
 MMX-OBJS-$(CONFIG_DSPUTIL)             += x86/dsputil_mmx.o             \
                                           x86/fdct.o                    \
+                                          x86/fpel_mmx.o                \
                                           x86/idct_mmx_xvid.o           \
                                           x86/idct_sse2_xvid.o          \
                                           x86/simple_idct.o             \
diff --git a/libavcodec/x86/dsputil_mmx.c b/libavcodec/x86/dsputil_mmx.c
index a8eeba8..77d79ea 100644
--- a/libavcodec/x86/dsputil_mmx.c
+++ b/libavcodec/x86/dsputil_mmx.c
@@ -255,68 +255,6 @@ void ff_add_pixels_clamped_mmx(const int16_t *block, uint8_t *pixels,
     } while (--i);
 }
 
-static void put_pixels8_mmx(uint8_t *block, const uint8_t *pixels,
-                            ptrdiff_t line_size, int h)
-{
-    __asm__ volatile (
-        "lea   (%3, %3), %%"REG_a"      \n\t"
-        ".p2align     3                 \n\t"
-        "1:                             \n\t"
-        "movq  (%1    ), %%mm0          \n\t"
-        "movq  (%1, %3), %%mm1          \n\t"
-        "movq     %%mm0, (%2)           \n\t"
-        "movq     %%mm1, (%2, %3)       \n\t"
-        "add  %%"REG_a", %1             \n\t"
-        "add  %%"REG_a", %2             \n\t"
-        "movq  (%1    ), %%mm0          \n\t"
-        "movq  (%1, %3), %%mm1          \n\t"
-        "movq     %%mm0, (%2)           \n\t"
-        "movq     %%mm1, (%2, %3)       \n\t"
-        "add  %%"REG_a", %1             \n\t"
-        "add  %%"REG_a", %2             \n\t"
-        "subl        $4, %0             \n\t"
-        "jnz         1b                 \n\t"
-        : "+g"(h), "+r"(pixels),  "+r"(block)
-        : "r"((x86_reg)line_size)
-        : "%"REG_a, "memory"
-        );
-}
-
-static void put_pixels16_mmx(uint8_t *block, const uint8_t *pixels,
-                             ptrdiff_t line_size, int h)
-{
-    __asm__ volatile (
-        "lea   (%3, %3), %%"REG_a"      \n\t"
-        ".p2align     3                 \n\t"
-        "1:                             \n\t"
-        "movq  (%1    ), %%mm0          \n\t"
-        "movq 8(%1    ), %%mm4          \n\t"
-        "movq  (%1, %3), %%mm1          \n\t"
-        "movq 8(%1, %3), %%mm5          \n\t"
-        "movq     %%mm0,  (%2)          \n\t"
-        "movq     %%mm4, 8(%2)          \n\t"
-        "movq     %%mm1,  (%2, %3)      \n\t"
-        "movq     %%mm5, 8(%2, %3)      \n\t"
-        "add  %%"REG_a", %1             \n\t"
-        "add  %%"REG_a", %2             \n\t"
-        "movq  (%1    ), %%mm0          \n\t"
-        "movq 8(%1    ), %%mm4          \n\t"
-        "movq  (%1, %3), %%mm1          \n\t"
-        "movq 8(%1, %3), %%mm5          \n\t"
-        "movq     %%mm0,  (%2)          \n\t"
-        "movq     %%mm4, 8(%2)          \n\t"
-        "movq     %%mm1,  (%2, %3)      \n\t"
-        "movq     %%mm5, 8(%2, %3)      \n\t"
-        "add  %%"REG_a", %1             \n\t"
-        "add  %%"REG_a", %2             \n\t"
-        "subl        $4, %0             \n\t"
-        "jnz         1b                 \n\t"
-        : "+g"(h), "+r"(pixels),  "+r"(block)
-        : "r"((x86_reg)line_size)
-        : "%"REG_a, "memory"
-        );
-}
-
 #define CLEAR_BLOCKS(name, n)                           \
 static void name(int16_t *blocks)                       \
 {                                                       \
@@ -1143,7 +1081,7 @@ static void gmc_mmx(uint8_t *dst, uint8_t *src,
 /* CAVS-specific */
 void ff_put_cavs_qpel8_mc00_mmx(uint8_t *dst, uint8_t *src, ptrdiff_t stride)
 {
-    put_pixels8_mmx(dst, src, stride, 8);
+    ff_put_pixels8_mmx(dst, src, stride, 8);
 }
 
 void ff_avg_cavs_qpel8_mc00_mmx(uint8_t *dst, uint8_t *src, ptrdiff_t stride)
@@ -1153,7 +1091,7 @@ void ff_avg_cavs_qpel8_mc00_mmx(uint8_t *dst, uint8_t *src, ptrdiff_t stride)
 
 void ff_put_cavs_qpel16_mc00_mmx(uint8_t *dst, uint8_t *src, ptrdiff_t stride)
 {
-    put_pixels16_mmx(dst, src, stride, 16);
+    ff_put_pixels16_mmx(dst, src, stride, 16);
 }
 
 void ff_avg_cavs_qpel16_mc00_mmx(uint8_t *dst, uint8_t *src, ptrdiff_t stride)
@@ -1165,7 +1103,7 @@ void ff_avg_cavs_qpel16_mc00_mmx(uint8_t *dst, uint8_t *src, ptrdiff_t stride)
 void ff_put_vc1_mspel_mc00_mmx(uint8_t *dst, const uint8_t *src,
                                ptrdiff_t stride, int rnd)
 {
-    put_pixels8_mmx(dst, src, stride, 8);
+    ff_put_pixels8_mmx(dst, src, stride, 8);
 }
 
 #if CONFIG_DIRAC_DECODER
@@ -1195,7 +1133,7 @@ void ff_ ## OPNAME2 ## _dirac_pixels32_ ## EXT(uint8_t *dst, const uint8_t *src[
 }
 
 #if HAVE_MMX_INLINE
-DIRAC_PIXOP(put, put, mmx)
+DIRAC_PIXOP(put, ff_put, mmx)
 DIRAC_PIXOP(avg, avg, mmx)
 #endif
 
diff --git a/libavcodec/x86/dsputil_mmx.h b/libavcodec/x86/dsputil_mmx.h
index 1b68161..a0a4cdb 100644
--- a/libavcodec/x86/dsputil_mmx.h
+++ b/libavcodec/x86/dsputil_mmx.h
@@ -155,6 +155,11 @@ void ff_add_pixels_clamped_mmx(const int16_t *block, uint8_t *pixels, int line_s
 void ff_put_pixels_clamped_mmx(const int16_t *block, uint8_t *pixels, int line_size);
 void ff_put_signed_pixels_clamped_mmx(const int16_t *block, uint8_t *pixels, int line_size);
 
+
+void ff_put_pixels8_mmx(uint8_t *block, const uint8_t *pixels,
+                        ptrdiff_t line_size, int h);
+void ff_put_pixels16_mmx(uint8_t *block, const uint8_t *pixels,
+                         ptrdiff_t line_size, int h);
 void ff_avg_pixels8_mmxext(uint8_t *block, const uint8_t *pixels,
                            ptrdiff_t line_size, int h);
 void ff_put_pixels8_mmxext(uint8_t *block, const uint8_t *pixels,
diff --git a/libavcodec/x86/fpel_mmx.c b/libavcodec/x86/fpel_mmx.c
new file mode 100644
index 0000000..faa1b03
--- /dev/null
+++ b/libavcodec/x86/fpel_mmx.c
@@ -0,0 +1,94 @@
+/*
+ * MMX-optimized avg/put pixel routines
+ *
+ * Copyright (c) 2000, 2001 Fabrice Bellard
+ * Copyright (c) 2002-2004 Michael Niedermayer <michaelni@gmx.at>
+ *
+ * This file is part of FFmpeg.
+ *
+ * FFmpeg is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * FFmpeg is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with FFmpeg; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#include <stddef.h>
+#include <stdint.h>
+
+#include "config.h"
+#include "dsputil_mmx.h"
+
+#if HAVE_MMX_INLINE
+
+void ff_put_pixels8_mmx(uint8_t *block, const uint8_t *pixels,
+                        ptrdiff_t line_size, int h)
+{
+    __asm__ volatile (
+        "lea   (%3, %3), %%"REG_a"      \n\t"
+        ".p2align     3                 \n\t"
+        "1:                             \n\t"
+        "movq  (%1    ), %%mm0          \n\t"
+        "movq  (%1, %3), %%mm1          \n\t"
+        "movq     %%mm0, (%2)           \n\t"
+        "movq     %%mm1, (%2, %3)       \n\t"
+        "add  %%"REG_a", %1             \n\t"
+        "add  %%"REG_a", %2             \n\t"
+        "movq  (%1    ), %%mm0          \n\t"
+        "movq  (%1, %3), %%mm1          \n\t"
+        "movq     %%mm0, (%2)           \n\t"
+        "movq     %%mm1, (%2, %3)       \n\t"
+        "add  %%"REG_a", %1             \n\t"
+        "add  %%"REG_a", %2             \n\t"
+        "subl        $4, %0             \n\t"
+        "jnz         1b                 \n\t"
+        : "+g"(h), "+r"(pixels),  "+r"(block)
+        : "r"((x86_reg)line_size)
+        : "%"REG_a, "memory"
+        );
+}
+
+void ff_put_pixels16_mmx(uint8_t *block, const uint8_t *pixels,
+                         ptrdiff_t line_size, int h)
+{
+    __asm__ volatile (
+        "lea   (%3, %3), %%"REG_a"      \n\t"
+        ".p2align     3                 \n\t"
+        "1:                             \n\t"
+        "movq  (%1    ), %%mm0          \n\t"
+        "movq 8(%1    ), %%mm4          \n\t"
+        "movq  (%1, %3), %%mm1          \n\t"
+        "movq 8(%1, %3), %%mm5          \n\t"
+        "movq     %%mm0,  (%2)          \n\t"
+        "movq     %%mm4, 8(%2)          \n\t"
+        "movq     %%mm1,  (%2, %3)      \n\t"
+        "movq     %%mm5, 8(%2, %3)      \n\t"
+        "add  %%"REG_a", %1             \n\t"
+        "add  %%"REG_a", %2             \n\t"
+        "movq  (%1    ), %%mm0          \n\t"
+        "movq 8(%1    ), %%mm4          \n\t"
+        "movq  (%1, %3), %%mm1          \n\t"
+        "movq 8(%1, %3), %%mm5          \n\t"
+        "movq     %%mm0,  (%2)          \n\t"
+        "movq     %%mm4, 8(%2)          \n\t"
+        "movq     %%mm1,  (%2, %3)      \n\t"
+        "movq     %%mm5, 8(%2, %3)      \n\t"
+        "add  %%"REG_a", %1             \n\t"
+        "add  %%"REG_a", %2             \n\t"
+        "subl        $4, %0             \n\t"
+        "jnz         1b                 \n\t"
+        : "+g"(h), "+r"(pixels),  "+r"(block)
+        : "r"((x86_reg)line_size)
+        : "%"REG_a, "memory"
+        );
+}
+
+#endif /* HAVE_MMX_INLINE */
diff --git a/libavcodec/x86/hpeldsp_init.c b/libavcodec/x86/hpeldsp_init.c
index 33a6526..392f4bc 100644
--- a/libavcodec/x86/hpeldsp_init.c
+++ b/libavcodec/x86/hpeldsp_init.c
@@ -74,6 +74,10 @@ void ff_avg_pixels8_xy2_mmxext(uint8_t *block, const uint8_t *pixels,
 void ff_avg_pixels8_xy2_3dnow(uint8_t *block, const uint8_t *pixels,
                               ptrdiff_t line_size, int h);
 
+#define put_pixels8_mmx         ff_put_pixels8_mmx
+#define put_pixels16_mmx        ff_put_pixels16_mmx
+#define put_no_rnd_pixels8_mmx  ff_put_pixels8_mmx
+#define put_no_rnd_pixels16_mmx ff_put_pixels16_mmx
 
 #if HAVE_INLINE_ASM
 
@@ -133,74 +137,6 @@ void ff_avg_pixels8_xy2_3dnow(uint8_t *block, const uint8_t *pixels,
 
 #endif /* HAVE_YASM */
 
-
-#if HAVE_INLINE_ASM
-#define put_no_rnd_pixels16_mmx put_pixels16_mmx
-#define put_no_rnd_pixels8_mmx put_pixels8_mmx
-
-static void put_pixels8_mmx(uint8_t *block, const uint8_t *pixels,
-                            ptrdiff_t line_size, int h)
-{
-    __asm__ volatile (
-        "lea   (%3, %3), %%"REG_a"      \n\t"
-        ".p2align     3                 \n\t"
-        "1:                             \n\t"
-        "movq  (%1    ), %%mm0          \n\t"
-        "movq  (%1, %3), %%mm1          \n\t"
-        "movq     %%mm0, (%2)           \n\t"
-        "movq     %%mm1, (%2, %3)       \n\t"
-        "add  %%"REG_a", %1             \n\t"
-        "add  %%"REG_a", %2             \n\t"
-        "movq  (%1    ), %%mm0          \n\t"
-        "movq  (%1, %3), %%mm1          \n\t"
-        "movq     %%mm0, (%2)           \n\t"
-        "movq     %%mm1, (%2, %3)       \n\t"
-        "add  %%"REG_a", %1             \n\t"
-        "add  %%"REG_a", %2             \n\t"
-        "subl        $4, %0             \n\t"
-        "jnz         1b                 \n\t"
-        : "+g"(h), "+r"(pixels),  "+r"(block)
-        : "r"((x86_reg)line_size)
-        : "%"REG_a, "memory"
-        );
-}
-
-static void put_pixels16_mmx(uint8_t *block, const uint8_t *pixels,
-                             ptrdiff_t line_size, int h)
-{
-    __asm__ volatile (
-        "lea   (%3, %3), %%"REG_a"      \n\t"
-        ".p2align     3                 \n\t"
-        "1:                             \n\t"
-        "movq  (%1    ), %%mm0          \n\t"
-        "movq 8(%1    ), %%mm4          \n\t"
-        "movq  (%1, %3), %%mm1          \n\t"
-        "movq 8(%1, %3), %%mm5          \n\t"
-        "movq     %%mm0,  (%2)          \n\t"
-        "movq     %%mm4, 8(%2)          \n\t"
-        "movq     %%mm1,  (%2, %3)      \n\t"
-        "movq     %%mm5, 8(%2, %3)      \n\t"
-        "add  %%"REG_a", %1             \n\t"
-        "add  %%"REG_a", %2             \n\t"
-        "movq  (%1    ), %%mm0          \n\t"
-        "movq 8(%1    ), %%mm4          \n\t"
-        "movq  (%1, %3), %%mm1          \n\t"
-        "movq 8(%1, %3), %%mm5          \n\t"
-        "movq     %%mm0,  (%2)          \n\t"
-        "movq     %%mm4, 8(%2)          \n\t"
-        "movq     %%mm1,  (%2, %3)      \n\t"
-        "movq     %%mm5, 8(%2, %3)      \n\t"
-        "add  %%"REG_a", %1             \n\t"
-        "add  %%"REG_a", %2             \n\t"
-        "subl        $4, %0             \n\t"
-        "jnz         1b                 \n\t"
-        : "+g"(h), "+r"(pixels),  "+r"(block)
-        : "r"((x86_reg)line_size)
-        : "%"REG_a, "memory"
-        );
-}
-#endif /* HAVE_INLINE_ASM */
-
 #define SET_HPEL_FUNCS(PFX, IDX, SIZE, CPU)                                     \
     do {                                                                        \
         c->PFX ## _pixels_tab IDX [0] = PFX ## _pixels ## SIZE ## _     ## CPU; \